© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 10789
    Prev
    Next
    INDEX
    Explanations

    being there for someone

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    om
    1.76
    amı
    1.71
    amese
    1.70
    alang
    1.70
    ي
    1.69
    раи
    1.68
    aia
    1.64
    roy
    1.63
    omia
    1.61
    am
    1.60
    POSITIVE LOGITS
    屼
    2.07
    屽
    2.05
    вов
    2.05
     fieles
    2.01
    セプト
    1.99
    ExpNow
    1.93
     prestation
    1.93
     minuto
    1.93
     मौजूद
    1.92
     presencia
    1.91
    Activations Density 0.158%

    No Known Activations